All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>,
	Dave Chinner <david@fromorbit.com>,
	ceph-devel@vger.kernel.org, Chao Yu <yuchao0@huawei.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	"Darrick J. Wong" <darrick.wong@oracle.com>,
	Jaegeuk Kim <jaegeuk@kernel.org>,
	Jeff Layton <jlayton@kernel.org>,
	Johannes Thumshirn <jth@kernel.org>,
	linux-cifs@vger.kernel.org, <linux-ext4@vger.kernel.org>,
	linux-f2fs-devel@lists.sourceforge.net, <linux-mm@kvack.org>,
	<linux-xfs@vger.kernel.org>, Miklos Szeredi <miklos@szeredi.hu>,
	Steve French <sfrench@samba.org>, Ted Tso <tytso@mit.edu>,
	Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>
Subject: [PATCH 05/13] ext4: Convert to use mapping->invalidate_lock
Date: Tue, 25 May 2021 15:50:42 +0200	[thread overview]
Message-ID: <20210525135100.11221-5-jack@suse.cz> (raw)
In-Reply-To: <20210525125652.20457-1-jack@suse.cz>

Convert ext4 to use mapping->invalidate_lock instead of its private
EXT4_I(inode)->i_mmap_sem. This is mostly search-and-replace. By this
conversion we fix a long standing race between hole punching and read(2)
/ readahead(2) paths that can lead to stale page cache contents.

CC: <linux-ext4@vger.kernel.org>
CC: Ted Tso <tytso@mit.edu>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext4/ext4.h     | 10 ----------
 fs/ext4/extents.c  | 25 +++++++++++++-----------
 fs/ext4/file.c     | 13 +++++++------
 fs/ext4/inode.c    | 47 +++++++++++++++++-----------------------------
 fs/ext4/ioctl.c    |  4 ++--
 fs/ext4/super.c    | 13 +++++--------
 fs/ext4/truncate.h |  8 +++++---
 7 files changed, 50 insertions(+), 70 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 37002663d521..ed64b4b217a1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1077,15 +1077,6 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
-	/*
-	 * i_mmap_sem is for serializing page faults with truncate / punch hole
-	 * operations. We have to make sure that new page cannot be faulted in
-	 * a section of the inode that is being punched. We cannot easily use
-	 * i_data_sem for this since we need protection for the whole punch
-	 * operation and i_data_sem ranks below transaction start so we have
-	 * to occasionally drop it.
-	 */
-	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -2962,7 +2953,6 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
-extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
 extern void ext4_da_release_space(struct inode *inode, int to_free);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c84d6f1af6..8bb6b84c8a84 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4467,6 +4467,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 			    loff_t len, int mode)
 {
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	handle_t *handle = NULL;
 	unsigned int max_blocks;
 	loff_t new_size = 0;
@@ -4553,17 +4554,17 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * Prevent page faults from reinstantiating pages we have
 		 * released from page cache.
 		 */
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&mapping->invalidate_lock);
 
 		ret = ext4_break_layouts(inode);
 		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&mapping->invalidate_lock);
 			goto out_mutex;
 		}
 
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&mapping->invalidate_lock);
 			goto out_mutex;
 		}
 		/* Now release the pages and zero block aligned part of pages */
@@ -4572,7 +4573,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&mapping->invalidate_lock);
 		if (ret)
 			goto out_mutex;
 	}
@@ -5214,6 +5215,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	ext4_lblk_t punch_start, punch_stop;
 	handle_t *handle;
 	unsigned int credits;
@@ -5267,7 +5269,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -5282,15 +5284,15 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Write tail of the last page before removed range since it will get
 	 * removed from the page cache below.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	ret = filemap_write_and_wait_range(mapping, ioffset, offset);
 	if (ret)
 		goto out_mmap;
 	/*
 	 * Write data that will be shifted to preserve them when discarding
 	 * page cache below. We are also protected from pages becoming dirty
-	 * by i_mmap_sem.
+	 * by i_rwsem and invalidate_lock.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+	ret = filemap_write_and_wait_range(mapping, offset + len,
 					   LLONG_MAX);
 	if (ret)
 		goto out_mmap;
@@ -5343,7 +5345,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5360,6 +5362,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	handle_t *handle;
 	struct ext4_ext_path *path;
 	struct ext4_extent *extent;
@@ -5418,7 +5421,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -5519,7 +5522,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 816dedcbd541..f5993d3bd7b2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -704,22 +704,23 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 	 */
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	pfn_t pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vmf->vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		down_read(&mapping->invalidate_lock);
 retry:
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 					       EXT4_DATA_TRANS_BLOCKS(sb));
 		if (IS_ERR(handle)) {
-			up_read(&EXT4_I(inode)->i_mmap_sem);
+			up_read(&mapping->invalidate_lock);
 			sb_end_pagefault(sb);
 			return VM_FAULT_SIGBUS;
 		}
 	} else {
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		down_read(&mapping->invalidate_lock);
 	}
 	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
 	if (write) {
@@ -731,10 +732,10 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 		/* Handling synchronous page fault? */
 		if (result & VM_FAULT_NEEDDSYNC)
 			result = dax_finish_sync_fault(vmf, pe_size, pfn);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		up_read(&mapping->invalidate_lock);
 		sb_end_pagefault(sb);
 	} else {
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		up_read(&mapping->invalidate_lock);
 	}
 
 	return result;
@@ -756,7 +757,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= ext4_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index fe6045a46599..9db1bba28271 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3950,20 +3950,19 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return ret;
 }
 
-static void ext4_wait_dax_page(struct ext4_inode_info *ei)
+static void ext4_wait_dax_page(struct inode *inode)
 {
-	up_write(&ei->i_mmap_sem);
+	up_write(&inode->i_mapping->invalidate_lock);
 	schedule();
-	down_write(&ei->i_mmap_sem);
+	down_write(&inode->i_mapping->invalidate_lock);
 }
 
 int ext4_break_layouts(struct inode *inode)
 {
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct page *page;
 	int error;
 
-	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+	if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
 		return -EINVAL;
 
 	do {
@@ -3974,7 +3973,7 @@ int ext4_break_layouts(struct inode *inode)
 		error = ___wait_var_event(&page->_refcount,
 				atomic_read(&page->_refcount) == 1,
 				TASK_INTERRUPTIBLE, 0, 0,
-				ext4_wait_dax_page(ei));
+				ext4_wait_dax_page(inode));
 	} while (error == 0);
 
 	return error;
@@ -4005,9 +4004,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	if (ext4_has_inline_data(inode)) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&mapping->invalidate_lock);
 		ret = ext4_convert_inline_data(inode);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&mapping->invalidate_lock);
 		if (ret)
 			return ret;
 	}
@@ -4058,7 +4057,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -4131,7 +4130,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5426,11 +5425,11 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			inode_dio_wait(inode);
 		}
 
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&inode->i_mapping->invalidate_lock);
 
 		rc = ext4_break_layouts(inode);
 		if (rc) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&inode->i_mapping->invalidate_lock);
 			goto err_out;
 		}
 
@@ -5506,7 +5505,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				error = rc;
 		}
 out_mmap_sem:
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&inode->i_mapping->invalidate_lock);
 	}
 
 	if (!error) {
@@ -5983,10 +5982,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	 * data (and journalled aops don't know how to handle these cases).
 	 */
 	if (val) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&inode->i_mapping->invalidate_lock);
 		err = filemap_write_and_wait(inode->i_mapping);
 		if (err < 0) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&inode->i_mapping->invalidate_lock);
 			return err;
 		}
 	}
@@ -6019,7 +6018,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&inode->i_mapping->invalidate_lock);
 
 	/* Finally we can mark the inode as dirty. */
 
@@ -6063,7 +6062,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 
-	down_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&mapping->invalidate_lock);
 
 	err = ext4_convert_inline_data(inode);
 	if (err)
@@ -6176,7 +6175,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 out_ret:
 	ret = block_page_mkwrite_return(err);
 out:
-	up_read(&EXT4_I(inode)->i_mmap_sem);
+	up_read(&mapping->invalidate_lock);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 out_error:
@@ -6184,15 +6183,3 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	ext4_journal_stop(handle);
 	goto out;
 }
-
-vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	vm_fault_t ret;
-
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	ret = filemap_fault(vmf);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-
-	return ret;
-}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 31627f7dc5cd..cedc604726c2 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -148,7 +148,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		goto journal_err_out;
 	}
 
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&inode->i_mapping->invalidate_lock);
 	err = filemap_write_and_wait(inode->i_mapping);
 	if (err)
 		goto err_out;
@@ -256,7 +256,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&inode->i_mapping->invalidate_lock);
 journal_err_out:
 	unlock_two_nondirectories(inode, inode_bl);
 	iput(inode_bl);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7dc94f3e18e6..966fd5ca48e0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -90,12 +90,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
 /*
  * Lock ordering
  *
- * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
- * i_mmap_rwsem (inode->i_mmap_rwsem)!
- *
  * page fault path:
- * mmap_lock -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
- *   page lock -> i_data_sem (rw)
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
+ *   -> page lock -> i_data_sem (rw)
  *
  * buffered write path:
  * sb_start_write -> i_mutex -> mmap_lock
@@ -103,8 +100,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
  *   i_data_sem (rw)
  *
  * truncate:
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> transaction start ->
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
+ *   page lock
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
  *   i_data_sem (rw)
  *
  * direct IO:
@@ -1350,7 +1348,6 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
-	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 	ext4_fc_init_inode(&ei->vfs_inode);
 }
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index bcbe3668c1d4..b7242e08c9dd 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,14 +11,16 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	struct address_space *mapping = inode->i_mapping;
+
 	/*
 	 * We don't need to call ext4_break_layouts() because the blocks we
 	 * are truncating were never visible to userspace.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
-	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	down_write(&mapping->invalidate_lock);
+	truncate_inode_pages(mapping, inode->i_size);
 	ext4_truncate(inode);
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 }
 
 /*
-- 
2.26.2


WARNING: multiple messages have this Message-ID
From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: linux-cifs@vger.kernel.org,
	Damien Le Moal <damien.lemoal@wdc.com>,
	linux-ext4@vger.kernel.org, Ted Tso <tytso@mit.edu>,
	"Darrick J. Wong" <darrick.wong@oracle.com>,
	Jeff Layton <jlayton@kernel.org>,
	Steve French <sfrench@samba.org>,
	Dave Chinner <david@fromorbit.com>,
	Matthew Wilcox <willy@infradead.org>,
	linux-f2fs-devel@lists.sourceforge.net,
	Christoph Hellwig <hch@infradead.org>,
	linux-mm@kvack.org, Miklos Szeredi <miklos@szeredi.hu>,
	Jan Kara <jack@suse.cz>, Jaegeuk Kim <jaegeuk@kernel.org>,
	ceph-devel@vger.kernel.org, Johannes Thumshirn <jth@kernel.org>,
	linux-xfs@vger.kernel.org
Subject: [f2fs-dev] [PATCH 05/13] ext4: Convert to use mapping->invalidate_lock
Date: Tue, 25 May 2021 15:50:42 +0200	[thread overview]
Message-ID: <20210525135100.11221-5-jack@suse.cz> (raw)
In-Reply-To: <20210525125652.20457-1-jack@suse.cz>

Convert ext4 to use mapping->invalidate_lock instead of its private
EXT4_I(inode)->i_mmap_sem. This is mostly search-and-replace. By this
conversion we fix a long standing race between hole punching and read(2)
/ readahead(2) paths that can lead to stale page cache contents.

CC: <linux-ext4@vger.kernel.org>
CC: Ted Tso <tytso@mit.edu>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext4/ext4.h     | 10 ----------
 fs/ext4/extents.c  | 25 +++++++++++++-----------
 fs/ext4/file.c     | 13 +++++++------
 fs/ext4/inode.c    | 47 +++++++++++++++++-----------------------------
 fs/ext4/ioctl.c    |  4 ++--
 fs/ext4/super.c    | 13 +++++--------
 fs/ext4/truncate.h |  8 +++++---
 7 files changed, 50 insertions(+), 70 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 37002663d521..ed64b4b217a1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1077,15 +1077,6 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
-	/*
-	 * i_mmap_sem is for serializing page faults with truncate / punch hole
-	 * operations. We have to make sure that new page cannot be faulted in
-	 * a section of the inode that is being punched. We cannot easily use
-	 * i_data_sem for this since we need protection for the whole punch
-	 * operation and i_data_sem ranks below transaction start so we have
-	 * to occasionally drop it.
-	 */
-	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -2962,7 +2953,6 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
-extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
 extern void ext4_da_release_space(struct inode *inode, int to_free);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c84d6f1af6..8bb6b84c8a84 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4467,6 +4467,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 			    loff_t len, int mode)
 {
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	handle_t *handle = NULL;
 	unsigned int max_blocks;
 	loff_t new_size = 0;
@@ -4553,17 +4554,17 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * Prevent page faults from reinstantiating pages we have
 		 * released from page cache.
 		 */
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&mapping->invalidate_lock);
 
 		ret = ext4_break_layouts(inode);
 		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&mapping->invalidate_lock);
 			goto out_mutex;
 		}
 
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&mapping->invalidate_lock);
 			goto out_mutex;
 		}
 		/* Now release the pages and zero block aligned part of pages */
@@ -4572,7 +4573,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&mapping->invalidate_lock);
 		if (ret)
 			goto out_mutex;
 	}
@@ -5214,6 +5215,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	ext4_lblk_t punch_start, punch_stop;
 	handle_t *handle;
 	unsigned int credits;
@@ -5267,7 +5269,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -5282,15 +5284,15 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Write tail of the last page before removed range since it will get
 	 * removed from the page cache below.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	ret = filemap_write_and_wait_range(mapping, ioffset, offset);
 	if (ret)
 		goto out_mmap;
 	/*
 	 * Write data that will be shifted to preserve them when discarding
 	 * page cache below. We are also protected from pages becoming dirty
-	 * by i_mmap_sem.
+	 * by i_rwsem and invalidate_lock.
 	 */
-	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+	ret = filemap_write_and_wait_range(mapping, offset + len,
 					   LLONG_MAX);
 	if (ret)
 		goto out_mmap;
@@ -5343,7 +5345,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5360,6 +5362,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
+	struct address_space *mapping = inode->i_mapping;
 	handle_t *handle;
 	struct ext4_ext_path *path;
 	struct ext4_extent *extent;
@@ -5418,7 +5421,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -5519,7 +5522,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	ext4_journal_stop(handle);
 	ext4_fc_stop_ineligible(sb);
 out_mmap:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 816dedcbd541..f5993d3bd7b2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -704,22 +704,23 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 	 */
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	pfn_t pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vmf->vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		down_read(&mapping->invalidate_lock);
 retry:
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 					       EXT4_DATA_TRANS_BLOCKS(sb));
 		if (IS_ERR(handle)) {
-			up_read(&EXT4_I(inode)->i_mmap_sem);
+			up_read(&mapping->invalidate_lock);
 			sb_end_pagefault(sb);
 			return VM_FAULT_SIGBUS;
 		}
 	} else {
-		down_read(&EXT4_I(inode)->i_mmap_sem);
+		down_read(&mapping->invalidate_lock);
 	}
 	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
 	if (write) {
@@ -731,10 +732,10 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
 		/* Handling synchronous page fault? */
 		if (result & VM_FAULT_NEEDDSYNC)
 			result = dax_finish_sync_fault(vmf, pe_size, pfn);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		up_read(&mapping->invalidate_lock);
 		sb_end_pagefault(sb);
 	} else {
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+		up_read(&mapping->invalidate_lock);
 	}
 
 	return result;
@@ -756,7 +757,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= ext4_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index fe6045a46599..9db1bba28271 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3950,20 +3950,19 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return ret;
 }
 
-static void ext4_wait_dax_page(struct ext4_inode_info *ei)
+static void ext4_wait_dax_page(struct inode *inode)
 {
-	up_write(&ei->i_mmap_sem);
+	up_write(&inode->i_mapping->invalidate_lock);
 	schedule();
-	down_write(&ei->i_mmap_sem);
+	down_write(&inode->i_mapping->invalidate_lock);
 }
 
 int ext4_break_layouts(struct inode *inode)
 {
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct page *page;
 	int error;
 
-	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+	if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
 		return -EINVAL;
 
 	do {
@@ -3974,7 +3973,7 @@ int ext4_break_layouts(struct inode *inode)
 		error = ___wait_var_event(&page->_refcount,
 				atomic_read(&page->_refcount) == 1,
 				TASK_INTERRUPTIBLE, 0, 0,
-				ext4_wait_dax_page(ei));
+				ext4_wait_dax_page(inode));
 	} while (error == 0);
 
 	return error;
@@ -4005,9 +4004,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	if (ext4_has_inline_data(inode)) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&mapping->invalidate_lock);
 		ret = ext4_convert_inline_data(inode);
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&mapping->invalidate_lock);
 		if (ret)
 			return ret;
 	}
@@ -4058,7 +4057,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * Prevent page faults from reinstantiating pages we have released from
 	 * page cache.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&mapping->invalidate_lock);
 
 	ret = ext4_break_layouts(inode);
 	if (ret)
@@ -4131,7 +4130,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 out_mutex:
 	inode_unlock(inode);
 	return ret;
@@ -5426,11 +5425,11 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			inode_dio_wait(inode);
 		}
 
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&inode->i_mapping->invalidate_lock);
 
 		rc = ext4_break_layouts(inode);
 		if (rc) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&inode->i_mapping->invalidate_lock);
 			goto err_out;
 		}
 
@@ -5506,7 +5505,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				error = rc;
 		}
 out_mmap_sem:
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&inode->i_mapping->invalidate_lock);
 	}
 
 	if (!error) {
@@ -5983,10 +5982,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	 * data (and journalled aops don't know how to handle these cases).
 	 */
 	if (val) {
-		down_write(&EXT4_I(inode)->i_mmap_sem);
+		down_write(&inode->i_mapping->invalidate_lock);
 		err = filemap_write_and_wait(inode->i_mapping);
 		if (err < 0) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
+			up_write(&inode->i_mapping->invalidate_lock);
 			return err;
 		}
 	}
@@ -6019,7 +6018,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
-		up_write(&EXT4_I(inode)->i_mmap_sem);
+		up_write(&inode->i_mapping->invalidate_lock);
 
 	/* Finally we can mark the inode as dirty. */
 
@@ -6063,7 +6062,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 
-	down_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&mapping->invalidate_lock);
 
 	err = ext4_convert_inline_data(inode);
 	if (err)
@@ -6176,7 +6175,7 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 out_ret:
 	ret = block_page_mkwrite_return(err);
 out:
-	up_read(&EXT4_I(inode)->i_mmap_sem);
+	up_read(&mapping->invalidate_lock);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 out_error:
@@ -6184,15 +6183,3 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	ext4_journal_stop(handle);
 	goto out;
 }
-
-vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	vm_fault_t ret;
-
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	ret = filemap_fault(vmf);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-
-	return ret;
-}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 31627f7dc5cd..cedc604726c2 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -148,7 +148,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		goto journal_err_out;
 	}
 
-	down_write(&EXT4_I(inode)->i_mmap_sem);
+	down_write(&inode->i_mapping->invalidate_lock);
 	err = filemap_write_and_wait(inode->i_mapping);
 	if (err)
 		goto err_out;
@@ -256,7 +256,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&inode->i_mapping->invalidate_lock);
 journal_err_out:
 	unlock_two_nondirectories(inode, inode_bl);
 	iput(inode_bl);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7dc94f3e18e6..966fd5ca48e0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -90,12 +90,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
 /*
  * Lock ordering
  *
- * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
- * i_mmap_rwsem (inode->i_mmap_rwsem)!
- *
  * page fault path:
- * mmap_lock -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
- *   page lock -> i_data_sem (rw)
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
+ *   -> page lock -> i_data_sem (rw)
  *
  * buffered write path:
  * sb_start_write -> i_mutex -> mmap_lock
@@ -103,8 +100,9 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
  *   i_data_sem (rw)
  *
  * truncate:
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> i_mmap_rwsem (w) -> page lock
- * sb_start_write -> i_mutex -> i_mmap_sem (w) -> transaction start ->
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
+ *   page lock
+ * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start ->
  *   i_data_sem (rw)
  *
  * direct IO:
@@ -1350,7 +1348,6 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
-	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 	ext4_fc_init_inode(&ei->vfs_inode);
 }
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index bcbe3668c1d4..b7242e08c9dd 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,14 +11,16 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	struct address_space *mapping = inode->i_mapping;
+
 	/*
 	 * We don't need to call ext4_break_layouts() because the blocks we
 	 * are truncating were never visible to userspace.
 	 */
-	down_write(&EXT4_I(inode)->i_mmap_sem);
-	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	down_write(&mapping->invalidate_lock);
+	truncate_inode_pages(mapping, inode->i_size);
 	ext4_truncate(inode);
-	up_write(&EXT4_I(inode)->i_mmap_sem);
+	up_write(&mapping->invalidate_lock);
 }
 
 /*
-- 
2.26.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

  parent reply	other threads:[~2021-05-25 13:51 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-25 13:50 [f2fs-dev] [PATCH 0/13 v6] fs: Hole punch vs page cache filling races Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 01/13] mm: Fix comments mentioning i_mutex Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 02/13] documentation: Sync file_operations members with reality Jan Kara
2021-05-25 20:43   ` Darrick J. Wong
2021-05-25 13:50 ` [f2fs-dev] [PATCH 03/13] mm: Protect operations adding pages to page cache with invalidate_lock Jan Kara
2021-05-25 21:01   ` Darrick J. Wong
2021-05-26 10:00     ` Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 04/13] mm: Add functions to lock invalidate_lock for two mappings Jan Kara
2021-05-25 20:48   ` Darrick J. Wong
2021-05-26 10:07     ` Jan Kara
2021-05-26 12:11       ` Damien Le Moal
2021-05-26 13:45         ` Jan Kara
2021-05-26 15:25           ` Darrick J. Wong
2021-05-25 13:50 ` Jan Kara [this message]
2021-05-25 13:50 ` [f2fs-dev] [PATCH 06/13] ext2: Convert to using invalidate_lock Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 07/13] xfs: Convert to use invalidate_lock Jan Kara
2021-05-25 21:37   ` Darrick J. Wong
2021-05-26 10:18     ` Jan Kara
2021-05-26 15:32       ` Darrick J. Wong
2021-05-27 12:01         ` Jan Kara
2021-05-25 21:40   ` Dave Chinner
2021-05-26 10:20     ` Jan Kara
2021-05-26 13:42       ` Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 08/13] xfs: Convert double locking of MMAPLOCK to use VFS helpers Jan Kara
2021-05-25 21:41   ` Darrick J. Wong
2021-05-25 13:50 ` [f2fs-dev] [PATCH 09/13] zonefs: Convert to using invalidate_lock Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 10/13] f2fs: " Jan Kara
2021-05-26  9:55   ` Chao Yu
2021-05-25 13:50 ` [f2fs-dev] [PATCH 11/13] fuse: " Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 12/13] ceph: Fix race between hole punch and page fault Jan Kara
2021-05-25 13:50 ` [f2fs-dev] [PATCH 13/13] cifs: " Jan Kara

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210525135100.11221-5-jack@suse.cz \
    --to=jack@suse.cz \
    --cc=ceph-devel@vger.kernel.org \
    --cc=damien.lemoal@wdc.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=jaegeuk@kernel.org \
    --cc=jlayton@kernel.org \
    --cc=jth@kernel.org \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=sfrench@samba.org \
    --cc=tytso@mit.edu \
    --cc=willy@infradead.org \
    --cc=yuchao0@huawei.com \
    --subject='Re: [PATCH 05/13] ext4: Convert to use mapping->invalidate_lock' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.